Envisioned to be the next-generation Internet, the metaverse faces far more security challenges due to its large scale, distributed, and decentralized nature. While traditional third-party security solutions remain certain limitations such as scalability and Single Point of Failure (SPoF), numerous wearable  Augmented/Virtual Reality (AR/VR) devices with increasingly computational capacity can contribute underused resource to protect the metaverse. Realizing the potential of Collaborative Intrusion Detection System (CIDS) in the metaverse context, we propose MetaCIDS, a blockchain-based Federated Learning (FL) framework that allows metaverse users to: (i) collaboratively train an adaptable CIDS model based on their collected local data with privacy protection; (ii) utilize such the FL model to detect metaverse intrusion using the locally observed network traffic; (iii) submit verifiable intrusion alerts through blockchain transactions to obtain token-based reward. Security analysis shows that MetaCIDS can tolerate up to 33% malicious trainers during the training of FL models, while the verifiability of alerts offer resistance to Distributed Denial of Service (DDoS) attacks. Besides, experimental results illustrate the efficiency and feasibility of MetaCIDS.

Metaverse allows a 3D virtual mapping of the physical world to the digital world in which users interact with each other via digital avatars with a wide range of virtual activities. To realize this, the metaverse will inevitably employ numerous machine learning (ML) systems to enable the virtual-physical mapping process and offer intelligent virtual services to metaverse users. However, metaverse service providers (MSPs), who need ML models for their services (e.g., virtual events and healthcare services), may not have expertise or resources to build these underlying ML models. Besides, although ML models can be offered by a crowd of experienced ML workers (MLWs), the MLWs might not be able to collect the desirable data for training their ML models due to privacy issues and the large-scale, distributed nature of the metaverse. In this paper, we propose MetaCrowd, a blockchain-based ML crowdsourcing framework that aims to overcome the mentioned issues and make ML accessible to every metaverse user and service provider. Unlike traditional crowdsourcing systems which rely on central authorities, MetaCrowd is decentralized and automatic thanks to blockchain and smart contracts, thereby mitigating the single point of failure and trust issues. Experimental results illustrate the efficiency of MetaCrowd in both performance and cost. In addition, a decentralized application is also implemented and published widely to show its feasibility in practice.

In the current age of digital world with the emergence of metaverse, digital assets are increasingly recognized and become more and more valuable. Unlike real-world assets, managing digital contents is more challenging since their associated information might be leaked widely on the Internet, making them worthless. Traditional digital asset management (DAM) systems based on third-party authorities and centralized databases have various weaknesses, threatening the benefits of stakeholders. In this paper, we propose a blockchain-based DAM framework utilizing smart contract, InterPlanetary File System (IPFS), and multi-layer encryption mechanisms for access control of digital assets in the metaverse. Our proposed design eliminates the intervention of intermediaries and offers a wide range of advanced security features such as resistance against data leakage and data alteration without trust assumptions among participants. Besides, key features of blockchain are leveraged to provide the system with immutability, traceability and transparency of information. To prove the feasibility of our design, we build a Decentralized Application (DApp) operating as a marketplace for digital assets using the proposed DAM framework. Experimental results indicate that the framework is more cost-effective than existing platforms, while advanced security features are integrated and automation is maximized

Recent generative diffusion models are attracting enormous attention with various breakthroughs in text-to-image, text-guided image-to-image, and text-to-3D generation. In this paper, we propose MobileGen3D, a bridge between text-driven real-world-to-3D generation and real-time on-device rendering. Given several real-world images of a person/object and a text prompt, MobileGen3D can provide a 3D model of the given content which has been customized according to the text prompt and can be rendered on mobile devices in real-time. No additional 3D training data is required in our method. Based on neural light fields (NeLF), MobileGen3D speeds up the inference process dramatically compared to other 3D synthesis methods that rely on neural radiance fields (NeRF). As a result, we demonstrate that our method can generate high-resolution 3D contents with realistic edits and low disk storage requirement of just 6.48 MB. These 3D contents can be rendered directly by mobile devices and augmented/virtual reality devices with a high rendering speed of 61.2 FPS on our experimented iPhone 14. Our implementation is available with detailed guidelines at this page: https://github.com/tuanvu171/MobileGen3D

Metaverse is envisioned to operate on top of the Internet of Things (IoT) in which numerous IoT sensors and wearable devices continuously collect real-world data to reflect the physical world into its virtual counterpart. As a result, the metaverse not only inherits various security threats from the IoT network, but also faces far more sophisticated attacks related to virtual reality technology. As traditional security approaches show various limitations in the large-scale distributed metaverse such as single point of failure (SPoF) and scalability issue, this paper proposes MetaCIDS, a novel collaborative intrusion detection (CID) framework that leverages metaverse devices to collaboratively protect the metaverse. In MetaCIDS, a federated learning (FL) scheme based on unsupervised autoencoder and an attention-based supervised classifier enables metaverse users to train a CID model using their local network data, while the blockchain network allows metaverse users to utilize an on-chain model to detect intrusion network flows over their monitored local network traffic, then submit verifiable intrusion alerts to the blockchain to earn metaverse tokens. Security analysis shows that MetaCIDS can efficiently detect zero-day attacks (i.e., attacks unseen in the training data), while the training process is resistant to SPoF, data tampering, and up to 33% poisoning nodes thank to the blockchain consensus, reputation, and incentive mechanisms. Performance evaluation illustrates the efficiency of MetaCIDS with 96% to 99% detection accuracy on four different network intrusion datasets, supporting both multi-class detection using labeled data and anomaly detection trained on unlabeled data.

The emerging metaverse is envisioned as a virtual mapping of the real world, thus it would inevitably employ numerous Machine Learning (ML) frameworks to analyze and process massive data for the virtual-physical synchronization process. As a distributed ML paradigm, Federated Learning (FL) can naturally take advantage of numerous IoT, wearable devices, and edge, cloud servers under the metaverse infrastructure to train ML models with privacy guarantee. However, the large-scale and decentralized nature of the metaverse can pose significant challenges to traditional FL schemes, where there is a centralized server aggregating the local models received from local devices. It is not only vulnerable to Single Point of Failure (SPoF), but also lacks incentive mechanisms encouraging metaverse users to contribute their resource and data. In this paper, we propose BFLMeta, a blockchain-based FL scheme for the metaverse in which the aggregation process is performed in a decentralized manner, while the framework can estimate the non-IID degree of data to flexibly adjust blockchain committee size, thereby mitigating the impact of malicious aggregators. Security analysis shows that BFLMeta can resist SPoF, poisoning attack, privacy leakage, and sybil attack. Besides, our evaluation on computation, communication, and performance illustrates the efficiency of BFLMeta. Notably, BFLMeta can converge even with more than 50% poisoning nodes.

The Metaverse, which is emerging as the next-generation (NextG) Internet, offers an immersive 3D virtual world in which people can organize various virtual activities and interact with each other seamlessly through digital avatars. As the NextG Internet, however, the Metaverse also faces severe security risks inherited from its predecessor as well as various new emerging threats. Furthermore, the decentralized nature of the Metaverse even makes it more challenging to mitigate these issues in a large-scale setting with numerous interactive wearable devices such as augmented, virtual reality (AR/VR) headsets and haptic devices. In this article, we aim to analyze the security aspect of the Metaverse thoroughly with special discussions of solutions enabled by blockchain and machine learning (ML). Firstly, we present a 4-layer architecture of the Metaverse and discuss potential solutions for Metaverse security based on blockchain and ML. Next, we develop a decentralized collaborative intrusion detection system (CIDS) based on blockchain and federated learning (FL) that allows such the Metaverse users to collaboratively protect this digital world, thereby solving the scalability and single-point-of-failure (SPoF) issues of traditional security approaches, which may not be effective in protecting the Metaverse with increasingly sophisticated attacks. Finally, we outline some key challenges and discuss future research directions for Metaverse security.

Federated learning (FL) has emerged as a machine learning (ML) paradigm for distributed training without requiring trainers to share private data. Coevally, unmanned aerial vehicles (UAVs) become sufficiently powerful that they can contribute to training sophisticated ML models. Direct application of the conventional FL framework to a UAV swarm, however, could result in unnecessarily high communication and computation complexity. This paper aims to address this challenge by proposing a scalable and clustered FL framework for such large UAV swarms. Specifically, we develop a clustering scheme based on which the UAV-based wireless network is partitioned into different clusters coordinated by corresponding cluster-head UAVs forming a connected graph. While the cluster-head UAVs coordinate the ML model updates as in the conventional FL framework, we propose two intercluster model aggregation strategies to produce the final global model in each training round. Extensive numerical studies demonstrate the convergence and desirable trade-offs between training performance and communication efficiency of our proposed framework.